Releasesby IbisCortex Agent SDK (Public Preview)
PreviewyesterdayUnverifiedAdded Oct 14, 2026
The Cortex Agent SDK is now available in Public Preview for Python and TypeScript. Use the SDK to build applications that run Cortex Agents and Cortex Code, maintain conversations and threads, observe durable turns, and reconnect to long-running work.
Topics: AI agents, Developer tools, Coding agents
More Snowflake Cortex AI releases
Every Snowflake Cortex AI releaseSnowflake Decision with AI_COMPLETE (Private Preview)
With this release, we introduce the private preview of Snowflake Decision, a model available through AI_COMPLETE that evaluates text and structured data against user-defined questions.
Claude Haiku 5.5 model in the Cortex REST API (Preview)
The claude-haiku-5-5 model is now available in Public Preview in the Cortex REST API.
Data lineage for storage integrations, external tables, model monitors, and Cortex Search services
Data lineage now includes the following relationships:
Cortex Agent code execution tool (General availability)
The Cortex Agent code execution tool is now generally available. The code execution tool is a built-in tool that enables an agent to execute code during a conversation, so your agents can run scripts to process data, perform calculations, and produce visualizations.
Snowflake Native Apps: Observability for Cortex Agents
Observability for Cortex Agents in a Snowflake Native App now includes the following capabilities:
DCM Projects DEFINE SEMANTIC VIEW (General availability)
With this release, DEFINE SEMANTIC VIEW in DCM Projects is generally available. You can declaratively manage semantic view definitions, including tables, relationships, facts, dimensions, metrics, AI instructions, and verified queries.
Response caching for Cortex AI Functions
Snowflake Cortex AI Functions now automatically caches and reuses the results of AI_COMPLETE calls. When a query makes an identical AI_COMPLETE call more than once, Snowflake can return the stored result instead of running inference again, which lowers cost and speeds up query execution.
Cortex AI Function Evaluation for measuring quality (Public Preview)
Snowflake Cortex AI Function Evaluation is now available in public preview, enabling customers to measure the output quality, cost, and token usage of custom AI Functions and Cortex AI calls against labeled datasets.
Also shipped on Oct 13, 2026
Snowflake in October 2026What's included:
- Three training methods: Supervised fine-tuning (SFT) , direct preference optimization (DPO) , and reinforcement learning with group relative policy optimization (GRPO) . Each method trains a low-rank adapter (LoRA) or the full model weights. Custom loss functions : Train with any objective you compute in PyTorch from the model's log-probabilities.
The AI.AGG function is generally available (GA)
The AI.AGG function is generally available (GA). You can use this function to semantically aggregate unstructured input data based on natural language instructions.
BigQuery generative AI functions now support the gemini-4-argon model
BigQuery generative AI functions now support the gemini-4-argon model. This model is generally available .
Gemini 4 Argon in CodeMender (Preview)
CodeMender now supports Gemini 4 Argon. To use it, pass --model gemini-4-argon to cm find , cm verify , or cm fix . Gemini 3.8 Flash remains the default model. For more information, see Specifying the model .
Gemini 4 Argon and Gemini 4 Argon Cyber Permissive
Gemini 4 Argon ( gemini-4-argon ) is available in General Availability (GA) . Gemini 4 Argon is Google's frontier model that excels at deep work in complex, real-world tasks across domains including coding, finance, legal, cybersecurity, and science.
On-demand state repartitioning is now generally available
On-demand state repartitioning is now generally available. You can resize the number of shuffle partitions for a stateful Structured Streaming query or Lakeflow pipeline without losing checkpoint state. See On-demand state repartitioning for stateful streaming queries .